Skip to content
aicoolies logo
DeepSeek logo

DeepSeek Coder

State-of-the-art open-source code language models

DeepSeek Coder is a family of open-source code language models trained from scratch on 2 trillion tokens of code and natural language data. Available in sizes from 1B to 33B parameters, these models support 80+ programming languages with 16K context windows and fill-in-the-blank capabilities. DeepSeek Coder outperforms CodeLlama-34B on HumanEval and MBPP benchmarks. Code is MIT-licensed; weights use the DeepSeek License Agreement, which allows commercial use with use restrictions.

About DeepSeek Coder

DeepSeek Coder represents one of the strongest open-source code model families available, trained by Chinese AI lab DeepSeek on a carefully curated corpus of 87% code and 13% natural language across 80+ programming languages. The training data is organized at the project level, preserving cross-file dependencies and repository structure that help the models understand codebases holistically rather than treating each file in isolation. Models are available at 1B, 5.7B, 6.7B, and 33B parameter sizes to fit different hardware constraints.

The models excel at code completion, code generation from natural language descriptions, and fill-in-the-middle tasks where the model predicts missing code given surrounding context. The 16K token context window handles entire files and multi-file contexts effectively. On the HumanEval benchmark, DeepSeek Coder 33B achieves scores competitive with or exceeding GPT-3.5-turbo and CodeLlama-34B, while the smaller 6.7B model provides strong performance for teams with limited GPU resources.

With over 23,000 GitHub stars, DeepSeek Coder has gained significant adoption both in the Chinese developer ecosystem and internationally. The repository code is MIT-licensed, while the models are covered by the DeepSeek License Agreement, which permits commercial use subject to its use-based restrictions, and the models are available on Hugging Face in various quantized formats for efficient deployment. DeepSeek Coder serves as the foundation for many derivative fine-tuned models and has influenced the broader open-source code model landscape by demonstrating that training from scratch on code-focused data can outperform adapting general-purpose language models.

Pricing & Platform Specs

Pricing Summary

Open-weights code models, free to download and self-host. The repository code is MIT-licensed; the model weights are covered by the DeepSeek License Agreement (Model License), which permits commercial use subject to the use-based restrictions in its Attachment A.

full pricing breakdown →

Supported Platforms

Hugging Face, GGUF — 1B to 33B parameter sizes

Explore categories, tags & use cases

Categories

High-performance local LLM inference in C/C++

llama.cpp is the foundational C/C++ library with 75K+ GitHub stars powering local LLM inference on consumer hardware. Provides optimized CPU and GPU inference for quantized models in GGUF format. Supports LLaMA, Mistral, Phi, Gemma, and most open-weight families. Features 2-8 bit quantization for reduced memory, multi-GPU support, context extension, grammar-constrained output, and an OpenAI-compatible API server. The engine behind Ollama and LM Studio.

Open Source

Git forge for agent-human collaboration, with agent-scored Trails, regional Git hosting and session memory

Entire is a Git forge for teams that work with AI coding agents, founded by former GitHub CEO Thomas Dohmke. Trails replace the pull-request timeline with eval scores and findings from review agents on every push, plus merge gates. Repositories can be hosted natively in several regions or mirrored from GitHub, and the open-source Entire CLI records agent sessions and adds local-first code-graph and memory plugins. Platform features are free; review agents use prepaid usage credits.

freemiumOpen Source

Community experience

Sources & verification

Sources checked
Content verified

Verification dates are editorial checks. Routine CMS saves and automatic updatedAt timestamps do not advance them.

FAQ

What is DeepSeek Coder?

DeepSeek Coder is a family of open-source code language models trained from scratch on 2 trillion tokens of code and natural language data. Available in sizes from 1B to 33B parameters, these models support 80+ programming languages with 16K context windows and fill-in-the-blank capabilities. DeepSeek Coder outperforms CodeLlama-34B on HumanEval and MBPP benchmarks. Code is MIT-licensed; weights use the DeepSeek License Agreement, which allows commercial use with use restrictions.

Is DeepSeek Coder free?

Yes — DeepSeek Coder is open source and free to use. Open-weights code models, free to download and self-host. The repository code is MIT-licensed; the model weights are covered by the DeepSeek License Agreement (Model License), which permits commercial use subject to the use-based restrictions in its Attachment A.

Is DeepSeek Coder open source?

Yes — DeepSeek Coder is open source.

Is DeepSeek Coder still maintained?

Yes — DeepSeek Coder is active. Its listing was last verified on September 6, 2026.

What are the best DeepSeek Coder alternatives?

The first editor-selected DeepSeek Coder alternatives are llama.cpp, Entire.